A Better Match for Drivers and Riders: Reinforcement Learning at Lyft

Author:

Azagirre Xabi1,Balwally Akshay1,Candeli Guillaume1,Chamandy Nicholas1,Han Benjamin1,King Alona1,Lee Hyungjun1,Loncaric Martin1,Martin Sébastien2ORCID,Narasiman Vijay1,Qin Zhiwei (Tony)1,Richard Baptiste1,Smoot Sara1,Taylor Sean1,van Ryzin Garrett1,Wu Di1,Yu Fei1,Zamoshchin Alex1

Affiliation:

1. Lyft, San Francisco, California 94107;

2. Northwestern University, Evanston, Illinois 60208

Abstract

We used reinforcement learning to improve how Lyft matches drivers and riders. The change was implemented globally and led to more than $30 million per year in incremental driver revenue.

Publisher

Institute for Operations Research and the Management Sciences (INFORMS)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3